no code implementations • 14 Feb 2024 • Yuanyu Wan, Tong Wei, Mingli Song, Lijun Zhang
Previous studies have established $O(n^{5/4}\rho^{-1/2}\sqrt{T})$ and ${O}(n^{3/2}\rho^{-1}\log T)$ regret bounds for convex and strongly convex functions respectively, where $n$ is the number of local learners, $\rho<1$ is the spectral gap of the communication matrix, and $T$ is the time horizon.
1 code implementation • 14 Dec 2023 • Tong Wei, Bo-Lin Wang, Min-Ling Zhang
The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes.
1 code implementation • 21 Sep 2023 • Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang
In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data.
Novel Class Discovery Open-World Semi-Supervised Learning +1
1 code implementation • 18 Sep 2023 • Jiang-Xin Shi, Tong Wei, Zhi Zhou, Xin-Yan Han, Jie-Jing Shao, Yu-Feng Li
In this paper, we propose PEL, a fine-tuning method that can effectively adapt pre-trained models to long-tailed recognition tasks in fewer than 20 epochs without the need for extra data.
Ranked #1 on Long-tail Learning on CIFAR-100-LT (ρ=10) (using extra training data)
Fine-Grained Image Classification Long-tail learning with class descriptors
no code implementations • ICCV 2023 • Xiaoyong Lu, Yaping Yan, Tong Wei, Songlin Du
Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene.
no code implementations • 8 May 2023 • Tong Wei, Linlong Wu, Kumar Vijay Mishra, M. R. Bhavani Shankar
This surface is crucial for designing compact low-cost wideband wireless systems, wherein ultra-massive antenna arrays are required to compensate for the losses incurred by severe attenuation and diffraction.
1 code implementation • CVPR 2023 • Tong Wei, Kai Gan
While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in many real-world classification problems, existing LTSSL algorithms typically assume that the class distributions of labeled and unlabeled data are almost identical.
2 code implementations • ICCV 2023 • Tong Wei, Yash Patel, Alexander Shekhovtsov, Jiri Matas, Daniel Barath
We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.
4 code implementations • 8 Oct 2022 • Tong Wei, Zhen Mao, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang
Multi-label learning has attracted significant attention from both academic and industry field in recent decades.
no code implementations • 26 May 2022 • Tong Wei, Qian-Yu Liu, Jiang-Xin Shi, Wei-Wei Tu, Lan-Zhe Guo
TRAS transforms the imbalanced pseudo-label distribution of a traditional SSL model via a delicate function to enhance the supervisory signals for minority classes.
1 code implementation • ICCV 2023 • Tong Wei, Jiri Matas, Daniel Barath
We propose a new sampler for robust estimators that always selects the sample with the highest probability of consisting only of inliers.
no code implementations • 22 Oct 2021 • Tong Wei, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang
Deep neural networks have been shown to be very powerful methods for many supervised learning tasks.
no code implementations • 26 Aug 2021 • Tong Wei, Jiang-Xin Shi, Wei-Wei Tu, Yu-Feng Li
To overcome this limitation, we establish a new prototypical noise detection method by designing a distance-based metric that is resistant to label noise.
Ranked #25 on Image Classification on mini WebVision 1.0
no code implementations • ICCV 2021 • Zhi-Fan Wu, Tong Wei, Jianwen Jiang, Chaojie Mao, Mingqian Tang, Yu-Feng Li
The existence of noisy data is prevalent in both the training and testing phases of machine learning systems, which inevitably leads to the degradation of model performance.
Ranked #18 on Image Classification on mini WebVision 1.0
no code implementations • 9 Apr 2021 • Tong Wei, Linlong Wu, M. R. Bhavani Shankar
Beampattern synthesis is a key problem in many wireless applications.
no code implementations • 1 Jan 2021 • Tong Wei, Wei-Wei Tu, Yu-Feng Li
Extreme multi-label learning (XML) works to annotate objects with relevant labels from an extremely large label set.
1 code implementation • 19 Jul 2020 • Tong Wei, Junlin Hou and Rui Feng
According to the output of edge prediction, we design a fuzzy membership function to achieve more exact relationship representations for node classification.
no code implementations • 20 Apr 2020 • Tong Wei, Feng Shi, Hai Wang, Wei-Wei Tu. Yu-Feng Li
To facilitate supervised consistency, reliable negative examples are mined from unlabeled data due to the absence of negative samples.